Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    numbers related to quantities or measurements

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and statistics related to population and capacity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ayn
    -0.73
    ersen
    -0.72
    nington
    -0.70
    etsk
    -0.67
    plain
    -0.66
    kell
    -0.65
    leys
    -0.65
    pler
    -0.63
    arnaev
    -0.62
     grate
    -0.62
    POSITIVE LOGITS
     consecutive
    0.81
     million
    0.75
     magnitude
    0.74
     thousand
    0.73
    lbs
    0.70
    %-
    0.69
     billion
    0.68
     centimeters
    0.68
     hundred
    0.68
     000
    0.67
    Act Density 0.139%

    No Known Activations